FM-FCN:A Neural Network with Filtering Modules for Accurate Vital Signs Extraction  

作　　者：Fangfang Zhu Qichao Niu Xiang Li Qi Zhao Honghong Su Jianwei Shuai 

机构地区：[1]Department of Physics,and Fujian Provincial Key Laboratory for Soft Functional Materials Research,Xiamen University,Xiamen 361005,China [2]National Institute for Data Science in Health and Medicine,and State Key Laboratory of Cellular Stress Biology,Innovation Center for Cell Signaling Network,Xiamen University,Xiamen 361005,China [3]Vitalsilicon Technology Co.Ltd.,Jiaxing,Zhejiang 314006,China [4]School of Computer Science and Software Engineering,University of Science and Technology Liaoning,Anshan 114051,China [5]Yangtze Delta Region Institute of Tsinghua University,Zhejiang,Jiaxing 314006,China [6]Wenzhou Institute,University of Chinese Academy of Sciences,Wenzhou 325001,China [7]Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine,Vision and Brain Health),Wenzhou 325001,China

出　　处：《Research》2025年第1期92-106,共15页研究(英文)

基　　金：supported by Ministry of Science and Technology of the People’s Republic of China(STI2030-Major Projects 2021ZD0201900);National Natural Science Foundation of China(grant mo.12090052);Natural Science Foundation of Liaoning Province(grant no.2023-MS-288);Fundamental Research Funds for the Central Universities(grant no.20720230017);Basic Public Welfare Research Program of Zhejiang Province(grant no.LGF20F030005).

摘　　要：Neural networks excel at capturing local spatial patterns through convolutional modules,but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological signals.In this work,we propose a novel network named filtering module fully convolutional network(FM-FCN),which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress noise.First,instead of using a fully connected layer,we use an FCN to preserve the time-dimensional correlation information of physiological signals,enabling multiple cycles of signals in the network and providing a basis for signal processing.Second,we introduce the FM as a network module that adapts to eliminate unwanted interference,leveraging the structure of the filter.This approach builds a bridge between deep learning and signal processing methodologies.Finally,we evaluate the performance of FM-FCN using remote photoplethysmography.Experimental results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse(BVP)signal and heart rate(HR)accuracy.It substantially improves the quality of BVP waveform reconstruction,with a decrease of 20.23%in mean absolute error(MAE)and an increase of 79.95%in signal-to-noise ratio(SNR).Regarding HR estimation accuracy,FM-FCN achieves a decrease of 35.85%in MAE,29.65%in error standard deviation,and 32.88%decrease in 95%limits of agreement width,meeting clinical standards for HR accuracy requirements.The results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal extraction.The codes and datasets are available online at https://github.com/zhaoqi106/FM-FCN.

关 键 词：physiological signalsin filtering module fully convolutional network fm fcn which vital signs extraction amplify physiological signals convolutional modulesbut neural networks filtering module capturing local spatial patterns 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]